Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification
arXiv:1901.06129
Abstract
In this paper, we propose a unified Multi-Object Tracking (MOT) framework learning to make full use of long term and short term cues for handling complex cases in MOT scenes. Besides, for better association, we propose switcher-aware classification (SAC), which takes the potential identity-switch causer (switcher) into consideration. Specifically, the proposed framework includes a Single Object Tracking (SOT) sub-net to capture short term cues, a re-identification (ReID) sub-net to extract long term cues and a switcher-aware classifier to make matching decisions using extracted features from the main target and the switcher. Short term cues help to find false negatives, while long term cues avoid critical mistakes when occlusion happens, and the SAC learns to combine multiple cues in an effective way and improves robustness. The method is evaluated on the challenging MOT benchmarks and achieves the state-of-the-art results.
10 pages, 7 figures
References in corpus (3)
Cited by in corpus (23)
- Deep Learning for UAV-based Object Detection and Tracking: A Survey
- A Review of Tracking, Prediction and Decision Making Methods for Autonomous Driving
- Tracklets Predicting Based Adaptive Graph Tracking
- FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks
- Multiple Object Tracking by Flowing and Fusing
- MAT: Motion-Aware Multi-Object Tracking
- Fooling Detection Alone is Not Enough: First Adversarial Attack against Multiple Object Tracking
- GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization
- Tracking Objects as Points
- SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation
- Refinements in Motion and Appearance for Online Multi-Object Tracking
- TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model
- Local Metrics for Multi-Object Tracking
- Unsupervised Multiple Person Tracking using AutoEncoder-Based Lifted Multicuts
- Online Multiple Object Tracking with Cross-Task Synergy
- State-aware Re-identification Feature for Multi-target Multi-camera Tracking
- Enhancing the Association in Multi-Object Tracking via Neighbor Graph
- Efficient Global Multi-object Tracking Under Minimum-cost Circulation Framework
- Self-Supervised Multi-Object Tracking with Cross-Input Consistency
- City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones
- SQE: a Self Quality Evaluation Metric for Parameters Optimization in Multi-Object Tracking
- MOTS: Multiple Object Tracking for General Categories Based On Few-Shot Method
- End-to-End Multi-Object Tracking with Global Response Map